基于班级成员之间不需要普遍或恒定的特征的共享特征模式,在自然世界中很常见,并且在一系列特征上都超过了一多裂的分类。我们表明,阈值元学习者(例如原型网络)需要一个嵌入维度,该维度在与任务相关的功能数量中指数呈指数级,以模拟这些功能。相比之下,默认情况下,注意分类器(例如匹配网络)是多真的,并且能够通过线性嵌入维度解决这些问题。但是,我们发现,在存在任务核定特征的情况下,元学习问题固有的特征,注意模型容易受到错误分类的影响。为了应对这一挑战,我们提出了一种自我注意的特征选择机制,该机制可适应非歧视性特征。我们证明了我们的方法在元学习布尔功能以及合成和现实世界中的几个学习任务中的有效性。
translated by 谷歌翻译
在新课程训练时,几乎没有射击学习(FSL)方法通常假设具有准确标记的样品的清洁支持集。这个假设通常可能是不现实的:支持集,无论多么小,仍然可能包括标签错误的样本。因此,对标签噪声的鲁棒性对于FSL方法是实用的,但是这个问题令人惊讶地在很大程度上没有探索。为了解决FSL设置中标签错误的样品,我们做出了一些技术贡献。 (1)我们提供了简单而有效的特征聚合方法,改善了流行的FSL技术Protonet使用的原型。 (2)我们描述了一种嘈杂的噪声学习的新型变压器模型(TRANFS)。 TRANFS利用变压器的注意机制称重标记为错误的样品。 (3)最后,我们对迷你胶原和tieredimagenet的嘈杂版本进行了广泛的测试。我们的结果表明,TRANFS与清洁支持集的领先FSL方法相对应,但到目前为止,在存在标签噪声的情况下,它们的表现优于它们。
translated by 谷歌翻译
Humans can quickly learn new visual concepts, perhaps because they can easily visualize or imagine what novel objects look like from different views. Incorporating this ability to hallucinate novel instances of new concepts might help machine vision systems perform better low-shot learning, i.e., learning concepts from few examples. We present a novel approach to low-shot learning that uses this idea. Our approach builds on recent progress in meta-learning ("learning to learn") by combining a meta-learner with a "hallucinator" that produces additional training examples, and optimizing both models jointly. Our hallucinator can be incorporated into a variety of meta-learners and provides significant gains: up to a 6 point boost in classification accuracy when only a single training example is available, yielding state-of-the-art performance on the challenging ImageNet low-shot classification benchmark.
translated by 谷歌翻译
epiSodic学习是对几枪学习感兴趣的研究人员和从业者的流行练习。它包括在一系列学习问题(或剧集)中组织培训,每个人分为小型训练和验证子集,以模仿评估期间遇到的情况。但这总是必要吗?在本文中,我们调查了在集发作的级别使用非参数方法,例如最近邻居等方法的焦点学习的有用性。对于这些方法,我们不仅展示了广州学习的限制是如何不必要的,而是他们实际上导致利用培训批次的数据低效方式。我们通过匹配和原型网络进行广泛的消融实验,其中两个最流行的方法在集中的级别使用非参数方法。他们的“非焦化”对应物具有很大的更简单,具有较少的近似参数,并在多个镜头分类数据集中提高它们的性能。
translated by 谷歌翻译
We propose prototypical networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class. Prototypical networks learn a metric space in which classification can be performed by computing distances to prototype representations of each class. Compared to recent approaches for few-shot learning, they reflect a simpler inductive bias that is beneficial in this limited-data regime, and achieve excellent results. We provide an analysis showing that some simple design decisions can yield substantial improvements over recent approaches involving complicated architectural choices and meta-learning. We further extend prototypical networks to zero-shot learning and achieve state-of-theart results on the CU-Birds dataset.
translated by 谷歌翻译
现代深度学习需要大规模广泛标记的数据集进行培训。少量学习旨在通过有效地从少数标记的例子中学习来缓解这个问题。在先前提出的少量视觉分类器中,假设对分类器决定的特征歧管具有不相关的特征尺寸和均匀特征方差。在这项工作中,我们专注于通过提出以低标签制度运行的差异敏感的模型来解决这一假设引起的限制。第一种方法简单的CNAP,采用基于分层正规的Mahalanobis距离基于距离的分类器,与现有神经自适应特征提取器的状态相结合,以在元数据集,迷你成像和分层图像基准基准上实现强大性能。我们进一步将这种方法扩展到转换学习设置,提出转导压盖。这种转换方法将软k-means参数细化过程与两步任务编码器相结合,以实现使用未标记数据的改进的测试时间分类精度。转导CNAP在元数据集上实现了最先进的性能。最后,我们探讨了我们的方法(简单和转换)的使用“开箱即用”持续和积极的学习。大规模基准的广泛实验表明了这一点的鲁棒性和多功能性,相对说话,简单的模型。所有培训的模型检查点和相应的源代码都已公开可用。
translated by 谷歌翻译
很少有图像分类是一个具有挑战性的问题,旨在仅基于少量培训图像来达到人类的识别水平。少数图像分类的一种主要解决方案是深度度量学习。这些方法是,通过将看不见的样本根据距离的距离进行分类,可在强大的深神经网络中学到的嵌入空间中看到的样品,可以避免以少数图像分类的少数训练图像过度拟合,并实现了最新的图像表现。在本文中,我们提供了对深度度量学习方法的最新审查,以进行2018年至2022年的少量图像分类,并根据度量学习的三个阶段将它们分为三组,即学习功能嵌入,学习课堂表示和学习距离措施。通过这种分类法,我们确定了他们面临的不同方法和问题的新颖性。我们通过讨论当前的挑战和未来趋势进行了少量图像分类的讨论。
translated by 谷歌翻译
在过去的几年里,几年枪支学习(FSL)引起了极大的关注,以最大限度地减少标有标记的训练示例的依赖。FSL中固有的困难是处理每个课程的培训样本太少的含糊不清的歧义。为了在FSL中解决这一基本挑战,我们的目标是培训可以利用关于新颖类别的先前语义知识来引导分类器合成过程的元学习模型。特别是,我们提出了语义调节的特征注意力和样本注意机制,估计表示尺寸和培训实例的重要性。我们还研究了FSL的样本噪声问题,以便在更现实和不完美的环境中利用Meta-Meverys。我们的实验结果展示了所提出的语义FSL模型的有效性,而没有样品噪声。
translated by 谷歌翻译
Learning with limited data is a key challenge for visual recognition. Many few-shot learning methods address this challenge by learning an instance embedding function from seen classes and apply the function to instances from unseen classes with limited labels. This style of transfer learning is task-agnostic: the embedding function is not learned optimally discriminative with respect to the unseen classes, where discerning among them leads to the target task. In this paper, we propose a novel approach to adapt the instance embeddings to the target classification task with a set-to-set function, yielding embeddings that are task-specific and are discriminative. We empirically investigated various instantiations of such set-to-set functions and observed the Transformer is most effective -as it naturally satisfies key properties of our desired model. We denote this model as FEAT (few-shot embedding adaptation w/ Transformer) and validate it on both the standard few-shot classification benchmark and four extended few-shot learning settings with essential use cases, i.e., cross-domain, transductive, generalized few-shot learning, and low-shot learning. It archived consistent improvements over baseline models as well as previous methods, and established the new stateof-the-art results on two benchmarks.
translated by 谷歌翻译
机器学习模型通常会遇到与训练分布不同的样本。无法识别分布(OOD)样本,因此将该样本分配给课堂标签会显着损害模​​型的可靠性。由于其对在开放世界中的安全部署模型的重要性,该问题引起了重大关注。由于对所有可能的未知分布进行建模的棘手性,检测OOD样品是具有挑战性的。迄今为止,一些研究领域解决了检测陌生样本的问题,包括异常检测,新颖性检测,一级学习,开放式识别识别和分布外检测。尽管有相似和共同的概念,但分别分布,开放式检测和异常检测已被独立研究。因此,这些研究途径尚未交叉授粉,创造了研究障碍。尽管某些调查打算概述这些方法,但它们似乎仅关注特定领域,而无需检查不同领域之间的关系。这项调查旨在在确定其共同点的同时,对各个领域的众多著名作品进行跨域和全面的审查。研究人员可以从不同领域的研究进展概述中受益,并协同发展未来的方法。此外,据我们所知,虽然进行异常检测或单级学习进行了调查,但没有关于分布外检测的全面或最新的调查,我们的调查可广泛涵盖。最后,有了统一的跨域视角,我们讨论并阐明了未来的研究线,打算将这些领域更加紧密地融为一体。
translated by 谷歌翻译
很少的识别涉及训练图像分类器,以使用几个示例(Shot)在测试时间区分新颖概念。现有方法通常假定测试时间的射击号是事先知道的。这是不现实的,当火车和测试射击不匹配时,流行和基础方法的性能已被证明会受到影响。我们对该现象进行了系统的经验研究。与先前的工作一致,我们发现射击灵敏度在基于度量的几个学习者中广泛存在,但是与先前的工作相反,较大的神经体系结构为变化的测试拍摄提供了一定程度的内置鲁棒性。更重要的是,通过消除对样品噪声的敏感性,一种基于余弦距离的简单,以前已知但非常忽略了一类方法,可以极大地改善对射击变化的鲁​​棒性。我们为流行和最近的几个弹药分类器提供了余弦替代品,从而扩大了它们对现实环境的适用性。这些余弦模型一致地提高了射击力,超越先前的射击状态,并在一系列基准和架构上提供竞争精度,包括在非常低的射击方案中取得的显着增长。
translated by 谷歌翻译
Few-shot learning has become essential for producing models that generalize from few examples. In this work, we identify that metric scaling and metric task conditioning are important to improve the performance of few-shot algorithms. Our analysis reveals that simple metric scaling completely changes the nature of few-shot algorithm parameter updates. Metric scaling provides improvements up to 14% in accuracy for certain metrics on the mini-Imagenet 5-way 5-shot classification task. We further propose a simple and effective way of conditioning a learner on the task sample set, resulting in learning a task-dependent metric space. Moreover, we propose and empirically test a practical end-to-end optimization procedure based on auxiliary task co-training to learn a task-dependent metric space. The resulting few-shot learning model based on the task-dependent scaled metric achieves state of the art on mini-Imagenet. We confirm these results on another few-shot dataset that we introduce in this paper based on CIFAR100. Our code is publicly available at https://github.com/ElementAI/TADAM.
translated by 谷歌翻译
Metric-based meta-learning is one of the de facto standards in few-shot learning. It composes of representation learning and metrics calculation designs. Previous works construct class representations in different ways, varying from mean output embedding to covariance and distributions. However, using embeddings in space lacks expressivity and cannot capture class information robustly, while statistical complex modeling poses difficulty to metric designs. In this work, we use tensor fields (``areas'') to model classes from the geometrical perspective for few-shot learning. We present a simple and effective method, dubbed hypersphere prototypes (HyperProto), where class information is represented by hyperspheres with dynamic sizes with two sets of learnable parameters: the hypersphere's center and the radius. Extending from points to areas, hyperspheres are much more expressive than embeddings. Moreover, it is more convenient to perform metric-based classification with hypersphere prototypes than statistical modeling, as we only need to calculate the distance from a data point to the surface of the hypersphere. Following this idea, we also develop two variants of prototypes under other measurements. Extensive experiments and analysis on few-shot learning tasks across NLP and CV and comparison with 20+ competitive baselines demonstrate the effectiveness of our approach.
translated by 谷歌翻译
很少有视觉识别是指从一些标记实例中识别新颖的视觉概念。通过将查询表示形式与类表征进行比较以预测查询实例的类别,许多少数射击的视觉识别方法采用了基于公制的元学习范式。但是,当前基于度量的方法通常平等地对待所有实例,因此通常会获得有偏见的类表示,考虑到并非所有实例在总结了类级表示的实例级表示时都同样重要。例如,某些实例可能包含无代表性的信息,例如过多的背景和无关概念的信息,这使结果偏差。为了解决上述问题,我们提出了一个新型的基于公制的元学习框架,称为实例自适应类别表示网络(ICRL-net),以进行几次视觉识别。具体而言,我们开发了一个自适应实例重新平衡网络,具有在生成班级表示,通过学习和分配自适应权重的不同实例中的自适应权重时,根据其在相应类的支持集中的相对意义来解决偏见的表示问题。此外,我们设计了改进的双线性实例表示,并结合了两个新型的结构损失,即,阶层内实例聚类损失和阶层间表示区分损失,以进一步调节实例重估过程并完善类表示。我们对四个通常采用的几个基准测试:Miniimagenet,Tieredimagenet,Cifar-FS和FC100数据集进行了广泛的实验。与最先进的方法相比,实验结果证明了我们的ICRL-NET的优势。
translated by 谷歌翻译
Representation learningLow-shot learning Feature extractor Base classes (many training examples)Classifier (base and novel categories) Novel classes (few training examples)Figure 1: Our low-shot learning benchmark in two phases: representation learning and low-shot learning. Modern recognition models use large labeled datasets like ImageNet to build good visual representations and train strong classifiers (representation learning).However, these datasets only contain a fixed set of classes. In many realistic scenarios, once deployed, the model might encounter novel classes that it also needs to recognize, but with very few training examples available (low-shot learning). We present two ways of significantly improving performance in this scenario: (1) a novel loss function for representation learning that leads to better visual representations that generalize well, and (2) a method for hallucinating additional examples for the data-starved novel classes.
translated by 谷歌翻译
无法解释的黑框模型创建场景,使异常引起有害响应,从而造成不可接受的风险。这些风险促使可解释的人工智能(XAI)领域通过评估黑盒神经网络中的局部解释性来改善信任。不幸的是,基本真理对于模型的决定不可用,因此评估仅限于定性评估。此外,可解释性可能导致有关模型或错误信任感的不准确结论。我们建议通过探索Black-Box模型的潜在特征空间来从用户信任的有利位置提高XAI。我们提出了一种使用典型的几弹网络的Protoshotxai方法,该方法探索了不同类别的非线性特征之间的对比歧管。用户通过扰动查询示例的输入功能并记录任何类的示例子集的响应来探索多种多样。我们的方法是第一个可以将其扩展到很少的网络的本地解释的XAI模型。我们将ProtoShotxai与MNIST,Omniglot和Imagenet的最新XAI方法进行了比较,以进行定量和定性,Protoshotxai为模型探索提供了更大的灵活性。最后,Protoshotxai还展示了对抗样品的新颖解释和检测。
translated by 谷歌翻译
基于签名的技术使数学洞察力洞悉不断发展的数据的复杂流之间的相互作用。这些见解可以自然地转化为理解流数据的数值方法,也许是由于它们的数学精度,已被证明在数据不规则而不是固定的情况下分析流的数据以及数据和数据的尺寸很有用样本量均为中等。了解流的多模式数据是指数的:$ d $ d $的字母中的$ n $字母中的一个单词可以是$ d^n $消息之一。签名消除了通过采样不规则性引起的指数级噪声,但仍然存在指数量的信息。这项调查旨在留在可以直接管理指数缩放的域中。在许多问题中,可伸缩性问题是一个重要的挑战,但需要另一篇调查文章和进一步的想法。这项调查描述了一系列环境集足够小以消除大规模机器学习的可能性,并且可以有效地使用一小部分免费上下文和原则性功能。工具的数学性质可以使他们对非数学家的使用恐吓。本文中介绍的示例旨在弥合此通信差距,并提供从机器学习环境中绘制的可进行的工作示例。笔记本可以在线提供这些示例中的一些。这项调查是基于伊利亚·雪佛兰(Ilya Chevryev)和安德烈·科米利津(Andrey Kormilitzin)的早期论文,它们在这种机械开发的较早时刻大致相似。本文说明了签名提供的理论见解是如何在对应用程序数据的分析中简单地实现的,这种方式在很大程度上对数据类型不可知。
translated by 谷歌翻译
Few-shot classification aims to recognize unlabeled samples from unseen classes given only few labeled samples. The unseen classes and low-data problem make few-shot classification very challenging. Many existing approaches extracted features from labeled and unlabeled samples independently, as a result, the features are not discriminative enough. In this work, we propose a novel Cross Attention Network to address the challenging problems in few-shot classification. Firstly, Cross Attention Module is introduced to deal with the problem of unseen classes. The module generates cross attention maps for each pair of class feature and query sample feature so as to highlight the target object regions, making the extracted feature more discriminative. Secondly, a transductive inference algorithm is proposed to alleviate the low-data problem, which iteratively utilizes the unlabeled query set to augment the support set, thereby making the class features more representative. Extensive experiments on two benchmarks show our method is a simple, effective and computationally efficient framework and outperforms the state-of-the-arts.
translated by 谷歌翻译
我们介绍了在Neurips'22接受的Chalearn Meta学习系列中的新挑战的设计和基线结果,重点是“跨域”元学习。元学习旨在利用从以前的任务中获得的经验,以有效地解决新任务(即具有更好的性能,较少的培训数据和/或适度的计算资源)。尽管该系列中的先前挑战集中在域内几乎没有学习问题,但目的是有效地学习n-way K-shot任务(即N级培训示例的N班级分类问题),这项竞赛挑战了参与者的解决方案。从各种领域(医疗保健,生态学,生物学,制造业等)提出的“任何通道”和“任何镜头”问题,他们是为了人道主义和社会影响而被选为。为此,我们创建了Meta-Album,这是来自10个域的40个图像分类数据集的元数据,从中,我们从中以任何数量的“方式”(在2-20范围内)和任何数量的“镜头”来解释任务”(在1-20范围内)。竞争是由代码提交的,在Codalab挑战平台上进行了完全盲目测试。获奖者的代码将是开源的,从而使自动化机器学习解决方案的部署可以在几个域中进行几次图像分类。
translated by 谷歌翻译
It has been experimentally demonstrated that humans are able to learn in a manner that allows them to make predictions on categories for which they have not seen any examples (Malaviya et al., 2022). Sucholutsky and Schonlau (2020) have recently presented a machine learning approach that aims to do the same. They utilise synthetically generated data and demonstrate that it is possible to achieve sub-linear scaling and develop models that can learn to recognise N classes from M training samples where M is less than N - aka less-than-one shot learning. Their method was, however, defined for univariate or simple multivariate data (Sucholutsky et al., 2021). We extend it to work on large, high-dimensional and real-world datasets and empirically validate it in this new and challenging setting. We apply this method to learn previously unseen NLP tasks from very few examples (4, 8 or 16). We first generate compact, sophisticated less-than-one shot representations called soft-label prototypes which are fitted on training data, capturing the distribution of different classes across the input domain space. We then use a modified k-Nearest Neighbours classifier to demonstrate that soft-label prototypes can classify data competitively, even outperforming much more computationally complex few-shot learning methods.
translated by 谷歌翻译